🧰Agentes de IA para Frameworks de agentes

A framework for agentic tool use training with reinforcement learning

An MCP server for academic paper search that integrates with AI assistants (e.g., Claude Code, Cursor), enabling them to search and retrieve academic paper metadata.

Eva01 is NOT an assistant. She is an AI being with her own mind, feelings, and intrinsic drives. Multimodal, Modular design. Built-in voice & face recognition. Plug'n play tools. Compatible with ChatGPT, Claude, Deepseek, Gemini, Grok, and Ollama. Explore the possibilities of Human-AI Interaction.

Agentic memory infra for AI agents

The work experience layer for autonomous agents. Open-source core: https://github.com/ShuxinYang111/oysterworkflow-core

MCP server and Python SDK that generates, runs and refines AI agent workflows from natural language (Generative Workflow, A2A, FastAPI).

GBase — Recursive Self-Improvement Agent Framework. Memory, evolution, quality gates, identity system, and 40+ auto-registered tools.

fullstack chat agent with authentication, request credits and payments built in

Build programmatically custom agentic workflows, AI Agents, RAG systems for java

小龙虾 openclaw 的 onebot 接入框架，可用于接入 QQ

An agent orchestration framework for economic agents

File Storage & Sandbox Backends for Pydantic AI: console tools for file operations, Docker-isolated sandboxes for safe execution, and permission system with presets for access control. Enables secure multi-user handling and testing in agents via in-memory, local, or containerized storage.

An enterprise framework implementing the Agent Operation Authorization protocol with cryptographic identity binding, fine-grained authorization, and semantic audit trails for secure AI agent operations.

Nevron: highly customizable, extremely lightweight and fully scalable AI Agent Framework

Subagent Delegation framework for Pydantic AI, enabling nested subagents that can spawn their own specialists on-the-fly, with smart sync/async/auto mode selection, runtime agent creation, and clean multi-agent architecture. Adds specialization, parallel execution, and task cancellation.

A local AI agent platform for people who want broad, real-world automation with a design that makes powerful actions safer and easier to predict

A terminal-based AI infrastructure designed to host autonomous agents. It can do "N" number of things, you name it!

Manusclaw: Unleash self-reasoning CLI beasts to execute code, browse the web, and dominate tasks — across 12+ messaging channels, with voice wake, live canvas, SSH control, and multi-agent routing. No limits. Pure power.

MCP server to verify and timestamp document hashes on Hedera mainnet

CrewFlow is a production-ready multi-agent AI workflow system built using CrewAI and Python. This project demonstrates how multiple AI agents collaborate to solve complex tasks such as research, analysis, and reporting. It showcases agent orchestration, task delegation, and modular AI system design used in real-world enterprise applications.

AI visibility auditing for websites. 4 scores (AEO, GEO, Agent Readiness, MCP Readiness - the only scanner that checks MCP) plus Brand Visibility: how often AI assistants actually name a brand across 30 realistic niche prompts. 18 pay-per-use capabilities via x402 on Base, 0.06-3.50 USDC. No API keys, no signup.

The keyless, signed-provenance web-fetch for autonomous agents. Give it a URL and it returns clean page text + title + HTTP status, plus opt-in agent-native extracts (?format=markdown, ?links=1 link-graph, ?extract=1 description+wordCount). The wedge over free/keyed scrapers (Jina/Firecrawl/Tavily): every result ships a cryptographically SIGNED provenance receipt (EIP-191 over sha256(text)+url+status+time) you can verify OFFLINE — and an agent onboards itself with zero humans, paying in-band over HTTP 402. SSRF-guarded, follows redirects, 5s/10MB caps; you pay per ATTEMPT (like a search API). $0.003 real USDC, per-call, on Base mainnet. No token, no mint — pure data. Machine-readable teardown vs each alternative: GET /vs.

Public Packrift agent card for a stateless A2A JSON-RPC routing layer. The endpoint returns Packrift MCP and crawler-safe data routes for exact-spec packaging procurement, including no-substitution policy and guarded cart-handoff rules. Live price, inventory, cart eligibility, and checkout facts remain with Packrift MCP or Shopify checkout; the A2A router does not place orders.

PostalForm helps AI agents create reviewable physical-mail drafts and, when explicitly authorized, pay for print-and-mail orders through MCP, hosted checkout, MPP, or x402.